SQM Infrastructure Product Development AI Engineer

Northern Trust•Chicago, IL

11d•$80,800 - $133,400

About The Position

Northern Trust is seeking a hands-on AI Engineer with strong product development experience to design, build, and deploy enterprise-grade Generative AI solutions. The role combines expertise in LLMs, RAG, agentic AI, Python, Azure, and cloud-native engineering with a product mindset focused on scalability, reliability, security, and user experience. The engineer will work across the full product lifecycle, from architecture and prototyping through API development, deployment, evaluation, monitoring, and production support. The position involves collaborating with product owners, architects, engineering teams, and application, infrastructure, cloud, database, and operations teams to turn business requirements into scalable AI product capabilities and resolve production issues.

Requirements

Experience with Generative AI, large language models (LLMs), Azure OpenAI, RAG, prompt engineering, agentic AI or AI agents, and LLM evaluation and observability.
Experience with LangChain, LangGraph, and LangSmith.
Proficiency in Python, FastAPI, REST APIs, asynchronous/API development, and microservices architecture.
Experience with PostgreSQL, pgvector, vector embeddings, semantic/vector search, and RAG retrieval and indexing patterns.
Experience with Microsoft Azure, Azure Kubernetes Service (AKS), containers/Docker, cloud-native application development, CI/CD, and production deployment practices.
Product development experience translating business requirements into technical capabilities and designing reusable, maintainable AI architectures.
Ability to balance model quality, latency, cost, security, and scalability.
Experience designing enterprise APIs and integration patterns, establishing AI evaluation and quality measures, troubleshooting production LLM/RAG applications, and collaborating across engineering, architecture, product, QA, DevOps, and business teams.
Must be authorized to work in the U.S. without employment-based visa sponsorship now or in the future.

Nice To Haves

Strong hands-on experience developing enterprise GenAI/RAG products.
Experience building LangGraph-based agentic workflows.
Hands-on experience with LangSmith tracing and evaluation.
Experience deploying Python/FastAPI applications on AKS.
Experience with PostgreSQL/pgvector at production scale.
Understanding of LLM hallucination, grounding, context management, guardrails, and evaluation.
Familiarity with Azure identity, secrets management, monitoring, and enterprise security patterns.
Experience building internal developer, infrastructure, automation, operations, or knowledge-management AI products.

Responsibilities

Design and develop enterprise Generative AI and agentic AI applications using LangChain, LangSmith, and LangGraph.
Build multi-step and stateful AI workflows involving reasoning, tool integration, retrieval, and human-in-the-loop patterns.
Develop RAG solutions using PostgreSQL and pgvector for vector storage and semantic retrieval.
Integrate applications with Azure OpenAI and other LLM-based services.
Design effective prompts and reusable prompt patterns using advanced prompt engineering techniques.
Build scalable backend services and REST APIs using Python and FastAPI.
Develop evaluation and observability mechanisms to measure AI response quality, latency, reliability, and retrieval effectiveness.
Use LangSmith for tracing, evaluation, debugging, and observability of LLM and agent workflows.
Containerize and deploy AI services to Azure Kubernetes Service (AKS).
Design solutions using appropriate Azure services for identity, security, networking, storage, monitoring, and application integration.
Implement production-ready practices, including exception handling, logging, retries, API security, configuration management, and observability.
Work with product owners, architects, and engineering teams to convert business requirements into scalable AI product capabilities.
Participate in architecture and design reviews, code reviews, testing, deployment, troubleshooting, and ongoing product enhancement.
Evaluate emerging LLM, retrieval, agentic AI, and AI engineering techniques and apply them where they provide measurable product value.
Partner with application, infrastructure, cloud, database, and operations teams during major incidents and production issues to identify dependencies and resolve problems.
Own features through design, development, testing, deployment, and production stabilization.